Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.6629. Min Act: -0.1700
Data Index: 2615117 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5846. Min Act: -0.1700
Data Index: 2395825 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5690. Min Act: -0.1700
Data Index: 3470264 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5846. Min Act: -0.1700
Data Index: 6117145 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5690. Min Act: -0.1700
Data Index: 1305729 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5376. Min Act: -0.1700
Data Index: 4343716 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5376. Min Act: -0.1700
Data Index: 6095856 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5533. Min Act: -0.1700
Data Index: 5398368 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5063. Min Act: -0.1700
Data Index: 1194115 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5063. Min Act: -0.1700
Data Index: 4770628 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5220. Min Act: -0.1700
Data Index: 3645617 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.4907. Min Act: -0.1700
Data Index: 2874439 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.4750. Min Act: -0.1700
Data Index: 693798 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.4750. Min Act: -0.1700
Data Index: 3587701 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.5063. Min Act: -0.1700
Data Index: 8654502 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.4593. Min Act: -0.1700
Data Index: 8614130 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.4593. Min Act: -0.1700
Data Index: 6841216 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.4593. Min Act: -0.1700
Data Index: 8190266 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.4593. Min Act: -0.1700
Data Index: 3693267 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6629. Min Range: -3.6629
Max Act: 3.4280. Min Act: -0.1700
Data Index: 1458116 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19